{"total":290,"rows":[{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204,"area":null},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","cited_by_count":90,"area":null},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2510.13515","title":"UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning","created":"2025-10-15","cited_by_count":42,"area":null},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2309.14289","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"area":null},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2407.03471","title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","created":"2024-07-03","cited_by_count":32,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2305.14428","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24,"area":null},{"id":"2406.13807","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","created":"2024-06-19","cited_by_count":23,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","cited_by_count":20,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2408.03574","title":"Teach CLIP to Develop a Number Sense for Ordinal Regression","created":"2024-08-07","cited_by_count":20,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2310.16494","title":"Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction","created":"2023-10-25","cited_by_count":19,"area":null},{"id":"2406.18587","title":"Nomic Embed Vision: Expanding the Latent Space","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18,"area":null},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2410.05210","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2303.01502","title":"Computational Language Acquisition with Theory of Mind","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2403.18062","title":"ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition","created":"2024-03-26","cited_by_count":14,"area":null},{"id":"2502.19842","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2404.03539","title":"Is CLIP the main roadblock for fine-grained open-world perception?","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2403.19103","title":"Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2501.09833","title":"Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2305.14998","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2306.06212","title":"Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions","created":"2023-06-09","cited_by_count":11,"area":null},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2402.04492","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2404.13594","title":"Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers","created":"2024-04-21","cited_by_count":11,"area":null},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2401.05300","title":"I am a Strange Dataset: Metalinguistic Tests for Language Models","created":"2024-01-10","cited_by_count":10,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2503.18435","title":"On the Perception Bottleneck of VLMs for Chart Understanding","created":"2025-03-24","cited_by_count":10,"area":null},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2511.20561","title":"Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward","created":"2025-11-25","cited_by_count":10,"area":null},{"id":"2306.08167","title":"Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2407.17827","title":"Unified Lexical Representation for Interpretable Visual-Language Alignment","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2410.13826","title":"Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2503.18406","title":"Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null}],"next_cursor":"100"}